LangChain Quickstart¶

In this quickstart you will create a simple rag agent with langchain and learn how to log it and get feedback on an LLM response.

For evaluation, we will leverage the RAG triad of groundedness, context relevance and answer relevance.

Setup¶

Add API keys¶

For this quickstart you will need an Open AI key

In [ ]:

# !pip install trulens trulens-apps-langchain trulens-providers-openai openai langchain langchainhub langchain-openai langchain_community faiss-cpu bs4 tiktoken

# !pip install trulens trulens-apps-langchain trulens-providers-openai openai langchain langchainhub langchain-openai langchain_community faiss-cpu bs4 tiktoken

In [ ]:

import os

os.environ["OPENAI_API_KEY"] = "sk-proj-..."

import os os.environ["OPENAI_API_KEY"] = "sk-proj-..."

Import from LangChain and TruLens¶

In [ ]:

from trulens.apps.langchain import TruChain
from trulens.core import TruSession

session = TruSession()
session.reset_database()

from trulens.apps.langchain import TruChain from trulens.core import TruSession session = TruSession() session.reset_database()

Load documents¶

In [ ]:

from langchain_community.document_loaders import WebBaseLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
import bs4

# Load and chunk contents of the blog
loader = WebBaseLoader(
    web_paths=("https://lilianweng.github.io/posts/2023-06-23-agent/",),
    bs_kwargs=dict(
        parse_only=bs4.SoupStrainer(
            class_=("post-content", "post-title", "post-header")
        )
    ),
)
docs = loader.load()

from langchain_community.document_loaders import WebBaseLoader from langchain_text_splitters import RecursiveCharacterTextSplitter import bs4 # Load and chunk contents of the blog loader = WebBaseLoader( web_paths=("https://lilianweng.github.io/posts/2023-06-23-agent/",), bs_kwargs=dict( parse_only=bs4.SoupStrainer( class_=("post-content", "post-title", "post-header") ) ), ) docs = loader.load()

Create Vector Store¶

In [ ]:

from langchain_core.vectorstores import InMemoryVectorStore
from langchain_openai import OpenAIEmbeddings

vector_store = InMemoryVectorStore(embedding=OpenAIEmbeddings())

text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
all_splits = text_splitter.split_documents(docs)

# Index chunks
_ = vector_store.add_documents(documents=all_splits)

from langchain_core.vectorstores import InMemoryVectorStore from langchain_openai import OpenAIEmbeddings vector_store = InMemoryVectorStore(embedding=OpenAIEmbeddings()) text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200) all_splits = text_splitter.split_documents(docs) # Index chunks _ = vector_store.add_documents(documents=all_splits)

Create RAG¶

In [ ]:

import bs4
from langchain.agents import AgentState, create_agent
from langchain.messages import MessageLikeRepresentation

from langchain_openai import ChatOpenAI
from langchain.tools import tool

# Construct a tool for retrieving context
@tool(response_format="content_and_artifact")
def retrieve_context(query: str):
    """Retrieve information to help answer a query."""
    retrieved_docs = vector_store.similarity_search(query, k=2)
    serialized = "\n\n".join(
        (f"Source: {doc.metadata}\nContent: {doc.page_content}")
        for doc in retrieved_docs
    )
    return serialized, retrieved_docs

tools = [retrieve_context]
# If desired, specify custom instructions
prompt = (
    "You have access to a tool that retrieves context from a blog post. "
    "Use the tool to help answer user queries."
)

model = ChatOpenAI(model_name="gpt-5-nano", temperature=0)

agent = create_agent(model, tools, system_prompt=prompt)

import bs4 from langchain.agents import AgentState, create_agent from langchain.messages import MessageLikeRepresentation from langchain_openai import ChatOpenAI from langchain.tools import tool # Construct a tool for retrieving context @tool(response_format="content_and_artifact") def retrieve_context(query: str): """Retrieve information to help answer a query.""" retrieved_docs = vector_store.similarity_search(query, k=2) serialized = "\n\n".join( (f"Source: {doc.metadata}\nContent: {doc.page_content}") for doc in retrieved_docs ) return serialized, retrieved_docs tools = [retrieve_context] # If desired, specify custom instructions prompt = ( "You have access to a tool that retrieves context from a blog post. " "Use the tool to help answer user queries." ) model = ChatOpenAI(model_name="gpt-5-nano", temperature=0) agent = create_agent(model, tools, system_prompt=prompt)

Initialize Feedback Function(s)¶

In [ ]:

import numpy as np
from trulens.core import Feedback
from trulens.providers.openai import OpenAI

provider = OpenAI(model_engine="gpt-4.1-mini")

# Define a groundedness feedback function
f_groundedness = (
    Feedback(
        provider.groundedness_measure_with_cot_reasons, name="Groundedness"
    )
    .on_context(collect_list=True)
    .on_output()
)
# Question/answer relevance between overall question and answer.
f_answer_relevance = (
    Feedback(provider.relevance_with_cot_reasons, name="Answer Relevance")
    .on_input()
    .on_output()
)

# Context relevance between question and each context chunk.
f_context_relevance = (
    Feedback(
        provider.context_relevance_with_cot_reasons, name="Context Relevance"
    )
    .on_input()
    .on_context(collect_list=False)
    .aggregate(np.mean)  # choose a different aggregation method if you wish
)

import numpy as np from trulens.core import Feedback from trulens.providers.openai import OpenAI provider = OpenAI(model_engine="gpt-4.1-mini") # Define a groundedness feedback function f_groundedness = ( Feedback( provider.groundedness_measure_with_cot_reasons, name="Groundedness" ) .on_context(collect_list=True) .on_output() ) # Question/answer relevance between overall question and answer. f_answer_relevance = ( Feedback(provider.relevance_with_cot_reasons, name="Answer Relevance") .on_input() .on_output() ) # Context relevance between question and each context chunk. f_context_relevance = ( Feedback( provider.context_relevance_with_cot_reasons, name="Context Relevance" ) .on_input() .on_context(collect_list=False) .aggregate(np.mean) # choose a different aggregation method if you wish )

Instrument chain for logging with TruLens¶

In [ ]:

tru_recorder = TruChain(
    agent,
    app_name="ChatApplication",
    app_version="Base",
    feedbacks=[f_answer_relevance, f_context_relevance, f_groundedness],
)

tru_recorder = TruChain( agent, app_name="ChatApplication", app_version="Base", feedbacks=[f_answer_relevance, f_context_relevance, f_groundedness], )

Record agent invocation¶

In [ ]:

with tru_recorder as recording:
    query = "What is task decomposition?"
    agent.invoke({"messages": [{"role": "user", "content": query}]})

with tru_recorder as recording: query = "What is task decomposition?" agent.invoke({"messages": [{"role": "user", "content": query}]})

Check results

In [ ]:

session.get_leaderboard()

session.get_leaderboard()

In [ ]:

from trulens.dashboard import run_dashboard

run_dashboard(session=session)

from trulens.dashboard import run_dashboard run_dashboard(session=session)